Where to download the 'icp' dataset which should be put into 'data/kitti/icp' ?

[mtli77]

Hi @XuyangBai

Does the data/kitti/icp can be download from the web page KITTI Odometry website.? Cound you tell me which .zip is the icp data, and I should download? By the way, I have changed the CUDA version to 9.2 and tensorflow-gpu=1.12.3, it seems goes well now.

Waiting for your reply! Best regards!

[mtli77]

Hi @XuyangBai I try to generated the icp from FCGF project. Something went wrong:

Traceback (most recent call last):
  File "train.py", line 84, in <module>
    main(config)
  File "train.py", line 63, in main
    trainer.train()
  File "/disk/tia/FCGF/lib/trainer.py", line 124, in train
    val_dict = self._valid_epoch()
  File "/disk/tia/FCGF/lib/trainer.py", line 314, in _valid_epoch
    input_dict = data_loader_iter.next()
  File "/home/ubuntu/.conda/envs/py3-fcgf/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 363, in __next__
    data = self._next_data()
  File "/home/ubuntu/.conda/envs/py3-fcgf/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 989, in _next_data
    return self._process_data(data)
  File "/home/ubuntu/.conda/envs/py3-fcgf/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1014, in _process_data
    data.reraise()
  File "/home/ubuntu/.conda/envs/py3-fcgf/lib/python3.7/site-packages/torch/_utils.py", line 395, in reraise
    raise self.exc_type(msg)
AssertionError: Caught AssertionError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/ubuntu/.conda/envs/py3-fcgf/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 185, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/ubuntu/.conda/envs/py3-fcgf/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch
    return self.collate_fn(data)
  File "/disk/tia/FCGF/lib/data_loaders.py", line 71, in collate_pair_fn
    coords_batch0, feats_batch0 = ME.utils.sparse_collate(coords0, feats0)   AssertionError: Coordinate length 135925 != Feature length 0
  File "/home/ubuntu/.conda/envs/py3-fcgf/lib/python3.7/site-packages/MinkowskiEngine/utils/collation.py", line 124, in sparse_collate
    assert N == Nf, f"Coordinate length {N} != Feature length {Nf}"
AssertionError: Coordinate length 10927 != Feature length 2

Traceback (most recent call last):
  File "/home/ubuntu/.conda/envs/py3-fcgf/lib/python3.7/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/home/ubuntu/.conda/envs/py3-fcgf/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/disk/tia/FCGF/scripts/test_kitti.py", line 144, in <module>
    main(config)
  File "/disk/tia/FCGF/scripts/test_kitti.py", line 27, in main
    config, config.test_phase, 1, num_threads=config.test_num_workers, shuffle=True)
AttributeError: 'EasyDict' object has no attribute 'test_num_workers'

And I don't know how to solve this bug. Could you have some idea about it? Or could you please share the icp dataset with me? By the way, I tried to train the 3dmatch on FCGF before, but during the testing step, some similar data dimensions mismatch errors were reported. I opened an issue, and no one has responded to that until now.

Waiting for your reply! Best regards!

https://github.com/chrischoy/FCGF/issues/39

https://github.com/chrischoy/FCGF/issues/38

[XuyangBai]

I borrow the KITTI dataset class from FCGF repo, so basically they are the same. The icp folder is generated when you run the training code of KITTI for the first time. You may read the code here, it is easy to figure out which zip file should be downloaded from the KITTI website (laser data, poses). Good luck.

Best, Xuyang

[mtli77]

I borrow the KITTI dataset class from FCGF repo, so basically they are the same. The icp folder is generated when you run the training code of KITTI for the first time. You may read the code here, it is easy to figure out which zip file should be downloaded from the KITTI website (laser data, poses). Good luck.

Best, Xuyang

Thank you very much, the program has run correctly.